Itasca MCP

What is Itasca MCP about?

Itasca MCP bridges AI agents with ITASCA simulation software (PFC, FLAC, 3DEC, MPoint, MassFlow). Through natural conversation, agents can browse engine documentation, build models, submit long‑running tasks, monitor progress, and retrieve intermediate results without stopping simulations.

How to use Itasca MCP?

1. Prerequisites – Install an ITASCA engine (9.0+ recommended) and the uv tool.
2. Register the server – Add the MCP server to your AI client, e.g.:

   claude mcp add itasca-mcp -- uvx itasca-mcp
   

3. Start the bridge – Inside the ITASCA GUI, run the provided addon.py (copy‑paste into the IPython console or execute the file).
4. Interact – Ask the AI agent to call tools such as itasca_execute_code, itasca_browse_docs, or itasca_submit_task. The bridge syncs GUI actions, plots, and data files back to the agent.
5. Daily startup – For subsequent sessions simply run:

   import itasca_mcp_bridge
   itasca_mcp_bridge.start()
   

Key features of Itasca MCP

• Multi‑engine support (PFC, FLAC, 3DEC, MPoint, MassFlow) and multiple version corpora.
• Ten built‑in tools: five for documentation lookup and five for interactive execution (REPL, task submission, progress monitoring, interruption, history).
• Live REPL while a simulation runs, allowing state inspection and incremental scripting.
• Full lifecycle management of long‑running tasks.
• Automatic synchronization of GUI actions (commands, plots, file operations) with the AI agent.
• Agent‑started bridge; works with Claude Code, Codex CLI, Gemini CLI, Copilot CLI, OpenCode, and other MCP‑compatible clients.

Use cases of Itasca MCP

• Geotechnical testing – “Run a biaxial compression test on a dense specimen and plot the stress‑strain curve.”
• Slope stability – “Build a slope model in FLAC3D and calculate the factor of safety.”
• Tunnel design – “Model tunnel excavation in jointed rock with 3DEC and report block displacements.”
• Landslide simulation – “Simulate a landslide runout with MPoint and generate the final deposit profile.”
• Live monitoring – “Check the current unbalanced force of a running simulation without stopping it.”
• Documentation assistance – “Search the plot commands and create a contact‑force‑chain visualization.”
• Error checking – “Review the last console command for mistakes.”

FAQ from the Itasca MCP

• Do I need a bridge for documentation tools? No, the five documentation tools operate without a bridge.
• Which AI agents are supported? Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI, OpenCode, toyoura‑nagisa, and any client that implements the Model Context Protocol.
• Can I run multiple engines simultaneously? Yes, each engine instance can start its own bridge; the MCP server routes calls based on the software and version parameters.
• How are updates handled? The start() function checks PyPI for a newer bridge release and self‑upgrades before connecting.
• What if the bridge fails to start? Follow the troubleshooting section in the bootstrap guide (docs/agentic/itasca-mcp-bootstrap.md).

itasca-mcp

English | 简体中文

itasca>model new ;now, with LLM.

itasca-mcp connects AI agents to ITASCA's geomechanics simulation software — PFC, FLAC, 3DEC, MPoint, and MassFlow — through the Model Context Protocol. Browse documentation, run simulations, and execute code, all through natural conversation.

itasca>model solve ;LLM solves.

Tools (10)

5 documentation tools — browse and search the selected engine's commands, Python API, and reference docs. No bridge required.

5 execution tools — interactive REPL, task submission, progress monitoring, interruption, and history. Requires bridge.

Example Prompts

• "Run a biaxial compression test on a dense specimen and plot the stress–strain curve"
• "Build a slope model in FLAC3D and find the factor of safety"
• "Model a tunnel excavation in jointed rock with 3DEC and check block displacements around the opening"
• "Simulate a landslide runout with MPoint and report the final deposit profile"
• "The simulation is still running, check the current unbalanced force without stopping it"
• "Look up the plot commands in the docs, then plot the contact force chains of the current model"
• "The command I just typed in the console doesn't seem right, take a look"

First-time Setup

Prerequisites

• An ITASCA engine installed — PFC, FLAC, 3DEC, MPoint, or MassFlow. 9.0+ recommended; PFC 6.0 / 7.0, FLAC 7.0, and 3DEC 7.0 are also supported.
• uv installed (for uvx)
• An AI agent — Claude Code, Codex CLI, Gemini CLI, or any MCP-capable client

Agentic Setup (Recommended)

Copy this to your AI agent and let it self-configure:

Fetch and follow this bootstrap guide end-to-end:
https://raw.githubusercontent.com/yusong652/itasca-mcp/main/docs/agentic/itasca-mcp-bootstrap.md

Manual Setup

1. Register the MCP server with your agent.

Most agents register it with a single command:

# Claude Code
claude mcp add itasca-mcp -- uvx itasca-mcp

# Codex / Codex-cli
codex mcp add itasca-mcp -- uvx itasca-mcp

# Gemini CLI
gemini mcp add itasca-mcp uvx itasca-mcp

Or fill in the MCP config file manually:

{
  "mcpServers": {
    "itasca-mcp": {
      "command": "uvx",
      "args": ["itasca-mcp"]
    }
  }
}

2. Start the bridge from inside the ITASCA engine:

Download addon.py, then use either of these two flows inside the engine GUI (PFC, FLAC, 3DEC, ...):

• Copy the file contents into the engine's IPython console and run them
• Or download the file and execute it in the engine GUI

Verify

Restart your AI agent and ask it to call itasca_execute_code to verify the connection.

Daily Startup

Once first-time setup is done, each new engine session only needs the bridge re-started — run this in the engine's IPython console and you're back online:

import itasca_mcp_bridge
itasca_mcp_bridge.start()

start() checks PyPI for a newer bridge release and self-upgrades before starting. The MCP client config persists.

Features

• Multi-engine, multi-version corpus - command, Python API, and reference docs for PFC, FLAC, 3DEC, MPoint, and MassFlow across engine versions (PFC: 6.0/7.0/9.0, FLAC: 7.0/9.0, 3DEC: 7.0/9.0), selected via the software and version parameters
• Documentation agents can navigate - agents browse the engine command tree to discover capabilities and boundaries, reducing hallucinated commands, with plot item reference docs supplementing the official documentation
• Live REPL alongside running tasks - execute code while a simulation is running: check model state and intermediate results without stopping the task; also useful for quick iteration before writing a full script
• Task lifecycle management - submit long-running simulations, monitor progress, interrupt running tasks, and browse task history
• Sees what you do in the GUI - cells you run in the engine's IPython pane, commands you enter at its prompt, the plots and data files you open, close or switch to, the items you add to a plot, and the data files you execute from the editor all reach the agent on its next call, so you can work in the GUI and with the agent at the same time
• Agent-started bridge - an AI agent can start the bridge itself through the engine's console.exe
• Multi-client compatible - works with Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI, OpenCode, toyoura-nagisa, and other MCP clients

Troubleshooting

See Troubleshooting in the bootstrap guide.

Development

See Developer Guide: Install and Run from Source.

Contributing

PRs and issues are welcome! See CONTRIBUTING.md for where changes land and how the documentation corpus is structured, and the Developer Guide for the source install.

License

MIT - see LICENSE.